Türkiye Ulaşım Kaynaklı Enerji İhtiyacının Hibrit ANFIS-PSO Metodu ile Tahmini

Ülke ekonomisi ve refah seviyesinin yanısıra savunma güvenliği ve stratejik hedefler yönünden enerjiplanlaması büyük öneme sahiptir. Bu nedenle, enerji talebinin en doğru şekilde tahmini, ülke politikalarıaçısından kritik bir konudur. Son yıllarda, gelecekteki enerji talep seviyelerini en doğru şekilde tahminedebilmek için çeşitli yöntemler kullanılmaktadır. Bununla birlikte, farklı tahmin yöntemleri arasındanen uygun olanın seçilmesi gerekmektedir. Bu çalışmada, Türkiye'de yıllık ulaşım kaynaklı enerji talebinin(UKET) modellenmesi ve tahmin edilmesi için hibrit bir yöntem olan Uyarlamalı Ağ Tabanlı BulanıkÇıkarım Sistemleri (Adaptive-Network Based Fuzzy Inference Systems, ANFIS) ile Parçacık SürüOptimizasyon (PSO) algoritması birlikte kullanılmıştır. Modellerin geliştirilmesinde gayri safi yurtiçihâsıla (GSYİH), nüfus, yıllık toplam taşıt-km parametreleri ve yıllık trafiğe çıkan taşıt sayısı model girdileriolarak alınmıştır. Modellerin eğitim ve test aşamaları için 1970 ile 2016 yılları arasındaki verilerkullanılmıştır. En iyi yaklaşım olarak belirlenen ANFIS-PSO modeli Türkiye’nin 2017’den 2023’e kadarUKET tahmini için kullanılmıştır. Elde edilen sonuçlar, Türkiye'nin ulaşım kaynaklı enerji talebinin 7 yıllıkbir sürede 2016 yılındaki değerinin yaklaşık 1,2 katına çıkacağını göstermiştir.

Estimation of Turkey's Transportation Energy Demand by Hybrid ANFIS- PSO

In addition to the country's economy and wealth, defense planning and strategic planning have great prospects for energy planning. For this reason, the most accurate estimation of energy demand is a critical issue in terms of country politics. In recent years, various techniques have been used to predict future energy demand levels in the most accurate way. However, it is necessary to choose the best appropriate among the different estimation techniques. In this study, a hybrid method called Adaptive Network Based Fuzzy Inference Systems (ANFIS) and Particle Swarm Optimization (PSO) algorithm are used together to model and estimate the annual road transport-based energy demand in Turkey. In the development of the models, gross domestic product (GDP), population, annual total vehicle-km parameters and the annual number of vehicles registered to traffic were taken as model inputs. The data from 1970 to 2016 were used for the training and testing phases of the models. The ANFIS-PSO model, which has been identified as the best approach, has been used for estimating the transportation energy from 2017 to 2023 of Turkey. The results show that Turkey's transportation-related energy demand will rise to 1,2 times the value of 2016 in a 7-year period.

PDF

___

Anemangely M., Ramezanzadeh A., Tokhmechi B., 2017. Shear wave travel time estimation from petrophysical logs using ANFIS-PSO algorithm: A case study from Ab-Teymour Oilfield, J Nat Gas Sci Eng., 38, 373–387.
Ausati S., Amanollahi J., 2016. Assessing the accuracy of ANFIS, EEMD-GRNN, PCR, and MLR models in predicting PM2.5, Atmos Environ, 142, 465–474.
Barak S., Sadegh S.S., 2016. Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm, Int J Electr Power Energy Syst, 82, 92–104.
Baskan O., Haldenbilen S., Ceylan H., Ceylan H., 2012. Estimating transport energy demand using ant colony optimization, Energy Sources Part B Econ Planning, 7, 188–199.
Canyurt O.E., Ozturk H.K., Hepbasli A., Utlu Z., 2006. Genetic algorithm (GA) approaches for the transport energy demand estimation: model development and application, Energy Sources, Part A Recover Util Environ Eff, 28, 1405–1413.
Ceylan, H., Ceylan, H., Haldenbilen, S., Baskan, O., 2008. Transport energy modeling with meta-heuristic harmony search algorithm, an application to Turkey, Energy policy, 36(7), 2527-2535.
Chai J., Lu Q.-Y., Wang S.-Y., Lai K.K., 2016. Analysis of road transportation energy consumption demand in China, Transp Res Part D Transp Environ, 48, 112– 124.
Chen W., Panahi M., 2017. Pourghasemi H.R., Performance evaluation of GIS-based new ensemble data mining techniques of adaptive neuro-fuzzy inference system (ANFIS) with genetic algorithm (GA), differential evolution (DE), and particle swarm optimization (PSO) for landslide spatial modelling, CATENA, 157, 310–324.
Forouzanfar M., Doustmohammadi A., Hasanzadeh S., Shakouri G.H., 2012. Transport energy demand forecast using multi-level genetic programming, Appl Energy, 91, 496–503.
Haldenbilen S., 2006. Fuel price determination in transportation sector using predicted energy and transport demand, Energy Policy, 34(17), 3078-3086.
Jang, J.-S. R., 1993. ANFIS: Adaptive-Network-Based Fuzzy Inference System, Ieee Transactions on Systems, Man and Cybernetics, 23(3), 665-685.
Kennedy J., Eberhart R., 1995. Particle Swarm Optimization, Proc. IEEE International Conference on Neural Networks (ICNN), 4, 1942-1948.
Limanond T., Jomnonkwao S., Srikaew A., 2011. Projection of future transport energy demand of Thailand, Energy Policy, 39, 2754-2763.
Lu I.J., Lewis C., Lin S.J., 2009. The forecast of motor vehicle, energy demand and CO 2 emission from Taiwan’s road transportation sector, Energy Policy, 37, 2952–2961.
Mullai P., Arulselvi S., Ngo H.-H., Sabarathinam P.L., 2011. Experiments and ANFIS modelling for the biodegradation of penicillin-G wastewater using anaerobic hybrid reactor, Bioresour Technol, 102, 5492–5497.
Murat Y.S. and Ceylan H., 2006. Use of artificial neural networks for transport energy demand modeling. Energy Policy, 34, 3165–3172.
Prasad K., Gorai A.K., Goyal P., 2016. Development of ANFIS models for air quality forecasting and input optimization for reducing the computational cost and time, Atmos Environ., 128, 246–262.
Rezakazemi M., Dashti A., Asghari M., Shirazian S., 2017. H2-selective mixed matrix membranes modeling using ANFIS, PSO-ANFIS, GA-ANFIS, Int J Hydrogen Energy, 42, 15211–15225.
Rini, D. P., Shamsuddin, S. M., Yuhaniz, S. S., 2016. Particle swarm optimization for ANFIS interpretability and accuracy, Soft Computing, 20(1), 251-262.
Sarkheyli A., Zain A.M., Sharif S., 2015. Robust optimization of ANFIS based on a new modified GA, Neurocomputing, 166, 357–366.
Sonmez M., Akgüngör A.P. and Bektaş S., 2017. Estimating transportation energy demand in Turkey using the artificial bee colony algorithm, Energy, 122, 301–310.
Taylan O., Demirbaş A., 2016. Forecasting and analysis of energy consumption for transportation in the Kingdom of Saudi Arabia, Energy Sources Part B Econ Planning, 11, 1150–1157.
Zhang M., Mu H., Li G., Ning Y., 2009. Forecasting the transport energy demand based on PLSR method in China, Energy, 34, 1396–1400.
http://www.tuik.gov.tr, (07.10.2017)
http://www.iea.org/publications/freepublications/publi cation/EnergyPoliciesofIEACountriesTurkey.pdf, (21.09.2017)
http://data.worldbank.org/country/turkey, (27.08.2017)
http://www.trafik.gov.tr, (24.08.2017)
http://www.dektmk.org.tr, (21.07.2017)